© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 32273
    Prev
    Next
    INDEX
    Explanations

    references to brain anatomy and related medical findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    497
    +0.13
    0.6%
    11
    +0.12
    0.6%
    750
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    11
    +0.13
    0.08
    455
    +0.12
    0.11
    156
    +0.11
    0.07
    Negative Logits
    ivals
    -0.73
    successfully
    -0.72
     Impossible
    -0.72
     Survive
    -0.70
    \\\\\\\\
    -0.69
    Attempt
    -0.69
    WARNING
    -0.68
     Dragonbound
    -0.68
    cook
    -0.68
    porary
    -0.68
    POSITIVE LOGITS
     regions
    1.13
     cortical
    1.07
     cortex
    1.06
     thickness
    1.05
     tracts
    1.05
    yrus
    1.04
     connectivity
    1.04
     amygdala
    1.02
     prefrontal
    1.01
    insula
    0.98
    Activations Density 2.142%

    No Known Activations